反馈TensorFlow Eager模式下Keras自定义层示例的代码缺失问题

Hey folks, I noticed there's an issue with the example for building custom Keras layers in Eager mode on the TensorFlow official site. The __init__ method is missing a crucial line of code that's required to properly initialize the parent Layer class:

super(MySimpleLayer, self).__init__()

Without this line, your custom layer won't inherit the necessary core functionality from the base tf.keras.layers.Layer class, which can lead to unexpected behavior or errors when using the layer in your models.

Here's the full corrected code example (I also adjusted a small naming detail to align with Keras conventions):

class MySimpleLayer(tf.keras.layers.Layer):
    def __init__(self, output_units):
        super(MySimpleLayer, self).__init__()  # This line was missing in the original example
        self.output_units = output_units
    def build(self, input_shape):
        # The build method gets called the first time your layer is used.
        # Creating variables on build() allows you to make their shape depend
        # on the input shape and hence remove the need for the user to specify
        # full shapes. It is possible to create variables during __init__() if
        # you already know their full shapes.
        self.kernel = self.add_variable(
            "kernel", [input_shape[-1], self.output_units])
    # Standard call method to define the layer's forward pass
    def call(self, inputs):
        return tf.matmul(inputs, self.kernel)

内容的提问来源于stack exchange，提问作者MAltakrori